{"id":"W2951577137","doi":"10.48550/arxiv.1704.00057","title":"Frames: A Corpus for Adding Memory to Goal-Oriented Dialogue Systems","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; Université de Montréal","funders":"","keywords":"Computer science; Task (project management); Baseline (sea); Frame (networking); Presentation (obstetrics); Tracking (education); Artificial intelligence; Natural language processing; State (computer science); Human–computer interaction; Programming language; Psychology; Engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000606433,0.0004956854,0.0007441373,0.0004599739,0.0004784451,0.0005591232,0.003529485,0.0005266208,0.000003938764],"category_scores_gemma":[0.0003839448,0.0005606498,0.0003850948,0.0003677281,0.00009705404,0.000444489,0.002324896,0.0004471893,0.0002299393],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004458806,"about_ca_system_score_gemma":0.0004733379,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00158272,"about_ca_topic_score_gemma":0.0001674544,"domain_scores_codex":[0.9968162,0.0001690332,0.0003640706,0.001739013,0.0001778983,0.0007338446],"domain_scores_gemma":[0.9952781,0.0002964346,0.0005928752,0.002884696,0.0004192233,0.0005286437],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005170492,0.0003737114,0.003727095,0.001530364,0.0007956937,0.001656513,0.002906336,0.2355442,0.0005452147,0.7147812,0.03443573,0.003186808],"study_design_scores_gemma":[0.00505033,0.0008605208,0.001489202,0.002703023,0.0003872771,0.00006841349,0.0009546337,0.8645807,0.0008925152,0.02883037,0.08997259,0.004210431],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04708406,0.0002189854,0.93451,0.00008747042,0.009926497,0.002120255,0.0002521734,0.000529306,0.00527127],"genre_scores_gemma":[0.9921643,0.0000316954,0.002816696,0.000111064,0.000624965,0.00002988025,0.0000820799,0.00003974176,0.004099644],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9450802,"threshold_uncertainty_score":0.9996845,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06518538499493316,"score_gpt":0.2105848772668836,"score_spread":0.1453994922719504,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}